Boosting Few-Shot Learning via Attentive Feature Regularization

arXiv:2403.17025v1 Announce Type: new
Abstract: Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing operation weakens the feature representation due to the linear interpolation and the overlooking of the importance of specific channels. To solve these issues, this paper proposes attentive feature regularization (AFR) which aims to improve the feature representativeness and discriminability. In our …

abstract arxiv boosting capacity cs.cv feature few-shot few-shot learning however linear manifold novel objects recognition regularization representation samples training type via